Local ai | npm.io

Offload is an in-browser AI stack. It provides an SDK to run AI inference directly on your users' devices, increasing their data privacy and saving on inference costs.

ai webgpu local ai edge ai privacy local llm

1.2.1 • Published 9 months ago

Libraries and server to build AI applications. Adapters to various native bindings allowing local inference. Integrate it with your application, or use as a microservice.

local ai inference server model pool gpt4all node-llama-cpp transformers.js llama.cpp chatbot bot llm

1.0.0-beta.31 • Published 5 months ago

Libraries and server to build AI applications. Adapters to various native bindings allowing local inference. Integrate it with your application, or use as a microservice.

local ai inference server model pool gpt4all node-llama-cpp transformers.js llama.cpp chatbot bot llm

1.0.0-beta.19 • Published 9 months ago

Local ai Packages

offload-ai

inference-server

lllms